Vehicle trajectory time-space alignment method and device, computer equipment and vehicle

Abstract

The application provides a vehicle trajectory time-space alignment method and device, computer equipment and a vehicle. The method comprises: obtaining sparse first trajectory reference points output by a planning module, the time interval between adjacent first trajectory reference points being a planning period; generating a plurality of dense second trajectory reference points by time interpolation between two adjacent first trajectory reference points, the time interval between two adjacent second trajectory reference points being a control period; deducing vehicle current pose information based on a vehicle planar motion model in a time interval in which planning and control run asynchronously; performing coordinate conversion on the second trajectory reference points according to the current pose information, so that they are uniformly projected into a current vehicle body coordinate system; and outputting a reference trajectory sequence aligned with the control period. Through the above method, consistent alignment and dynamic reconstruction of the reference trajectory in the time dimension and the space dimension are realized, so that the chassis control module can obtain a continuous, smooth and executable reference trajectory.

Description

Technical Field

[0001] This application relates to the field of vehicle motion control technology, and in particular to a vehicle trajectory time-space alignment method, device, computer equipment, and vehicle. Background Technology

[0002] As intelligent driving systems continue to evolve towards higher levels of automation and active safety functions, higher demands are placed on the real-time performance, continuity, and stability of trajectory tracking control under high-dynamic conditions such as emergency obstacle avoidance, high-speed lane changes, and handling on low-adhesion surfaces. In these scenarios, the planning module is responsible for generating a reference trajectory that meets safety constraints, while the chassis control module needs to accurately track and execute this reference trajectory at a high control frequency to ensure that the vehicle maintains good controllability and stability even when approaching its dynamic limits.

[0003] In existing intelligent driving system architectures, the planning module and the chassis control module typically operate on different computing platforms and have different operating cycles. The planning module is affected by complex calculations such as perception fusion, path search, and decision-making algorithms, resulting in a relatively low output cycle; while the chassis control module needs to operate in closed loop at a higher frequency to cope with rapid changes in vehicle dynamics.

[0004] The inconsistency in time scale between the planning module and the chassis control module causes the control device to be unable to obtain reference trajectory information that is strictly aligned with the current moment in multiple control cycles. This results in time lag and discontinuity in trajectory transmission and use across modules, which in turn adversely affects trajectory tracking performance and system stability in highly dynamic scenarios. Summary of the Invention

[0005] This application provides a vehicle trajectory time-space alignment method, device, computer equipment, and vehicle to solve the problem that the reference trajectory cannot be kept consistent with the current control cycle in the time and space dimensions when the planning module and chassis control module have inconsistent operating cycles and the vehicle's posture changes continuously.

[0006] Firstly, this application provides a vehicle trajectory time-space alignment method. The method includes: acquiring sparse first trajectory reference points output by a planning module, wherein the time interval between two adjacent first trajectory reference points is the planning cycle of the planning module; performing time interpolation between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points, wherein the time interval between two adjacent second trajectory reference points is the control cycle of a chassis control module, and the control cycle is less than the planning cycle; within a time interval during which the planning cycle and the control cycle operate asynchronously, inferring the current pose information of the vehicle in a global coordinate system based on a vehicle planar motion model; performing coordinate transformation on the second trajectory reference points according to the current pose information, so that the second trajectory reference points are uniformly projected onto the current vehicle body coordinate system; and outputting a reference trajectory sequence aligned with the control cycle for the chassis control module to perform trajectory tracking control.

[0007] Optionally, the information of each first trajectory reference point includes the vehicle's first reference lateral position, first reference heading angle, and first reference longitudinal velocity; the information of each second trajectory reference point includes the vehicle's second reference lateral position, second reference heading angle, and second reference longitudinal velocity; wherein, the step of performing time interpolation between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points includes: based on the time information of two adjacent first trajectory reference points, performing time interpolation on the first reference lateral position, first reference heading angle, and first reference longitudinal velocity of two adjacent first trajectory reference points respectively to generate multiple second reference lateral positions, second reference heading angles, and second reference longitudinal velocities corresponding to the control cycle.

[0008] Optionally, based on the time information of two adjacent first trajectory reference points, the piecewise cubic Hermite interpolation method is used to perform time interpolation on the first reference lateral position, the first reference heading angle, and the first reference longitudinal velocity.

[0009] Optionally, the step of inferring the vehicle's current pose information based on the vehicle's planar motion model includes: establishing a vehicle planar motion model based on the vehicle's lateral speed, longitudinal speed, and yaw rate; obtaining the vehicle's actual lateral speed, actual longitudinal speed, and actual yaw rate; calculating the vehicle's position change rate and heading angle change rate in the global coordinate system using the vehicle planar motion model based on the actual lateral speed, actual longitudinal speed, and actual yaw rate; and performing time integration on the position change rate and heading angle change rate to obtain a relative pose estimate of the vehicle in the global coordinate system relative to the most recent synchronization time. The relative pose estimate includes the vehicle's current position and current heading angle, and the relative pose estimate serves as the inferred current pose information of the vehicle in the global coordinate system.

[0010] Optionally, the method further includes: during the pose estimation process, when the control cycle is realigned with the planning cycle, resetting the relative pose estimate of the vehicle relative to the most recent synchronization time to zero.

[0011] Optionally, the step of performing coordinate transformation on the second trajectory reference point according to the current pose information so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system includes: performing a rotation transformation based on the current heading angle and a translation transformation based on the current position of the vehicle on the second trajectory reference point so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system.

[0012] Secondly, this application provides a computer device. The computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the vehicle trajectory time-space alignment method as described above.

[0013] Thirdly, this application provides a vehicle trajectory time-space alignment device. The device includes a trajectory data receiving module, a trajectory reconstruction module, a pose deduction module, a coordinate transformation module, and an output module. The trajectory data receiving module is used to acquire sparse first trajectory reference points output by a planning module, where the time interval between two adjacent first trajectory reference points is the planning cycle of the planning module. The trajectory reconstruction module is used to perform time interpolation between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points, where the time interval between two adjacent second trajectory reference points is the control cycle of a chassis control module, and the control cycle is less than the planning cycle. The pose deduction module is used to deduce the current pose information of the vehicle in the global coordinate system based on a vehicle planar motion model within the time interval between the asynchronous operation of the planning cycle and the control cycle. The coordinate transformation module is used to perform coordinate transformation on the second trajectory reference points according to the current pose information of the vehicle, so that the second trajectory reference points are uniformly projected onto the current vehicle body coordinate system. The output module is used to output a reference trajectory sequence aligned with the control cycle for the chassis control module to perform trajectory tracking control.

[0014] Fourthly, this application provides a vehicle. The vehicle includes the vehicle trajectory time-space alignment device described above.

[0015] Optionally, the vehicle further includes a planning module and a chassis control module. The planning module is connected to the chassis control module through the vehicle trajectory time-space alignment device. The planning module is used to generate sparse first trajectory reference points and send them to the vehicle trajectory time-space alignment device. The chassis control module is used to perform trajectory tracking control based on the reference trajectory sequence output by the vehicle trajectory time-space alignment device.

[0016] Using the above method, this application can receive sparse first trajectory reference points output by the planning module. Since the planning cycle of the planning module is longer than the control cycle of the chassis control module, the amount of trajectory data transmitted from the planning module to the chassis control module can be reduced, thus reducing the system communication burden. Furthermore, when the planning cycle and control cycle are inconsistent, a denser set of second trajectory reference points corresponding to the control cycle is generated by time interpolation between adjacent first trajectory reference points, enabling continuous and high-resolution reconstruction of the reference trajectory in the time dimension. Simultaneously, coordinate transformation is performed on the reference trajectory based on the vehicle's current pose information, achieving spatial alignment of the reference trajectory. Therefore, the chassis control module can obtain a continuous, smooth, and executable reference trajectory matching the current control cycle under high-dynamic conditions, thereby improving the stability and accuracy of trajectory tracking control. The vehicle trajectory time-space alignment method of this application is applicable to active safety scenarios such as high-speed obstacle avoidance and emergency lane changes. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0018] Figure 1 The diagram shown is a flowchart of a vehicle trajectory time-space alignment method according to an embodiment of this application.

[0019] Figure 2 As shown Figure 1 The flowchart shown is a detailed process for time interpolation of two adjacent first trajectory reference points.

[0020] Figure 3 As shown Figure 1 The diagram shown is a detailed flowchart of the simulation of the vehicle's current pose information.

[0021] Figure 4 As shown Figure 1 The flowchart shown illustrates the detailed process of coordinate transformation of the second trajectory reference point based on the vehicle's current pose information.

[0022] Figure 5 The diagram shown is a schematic block diagram of a vehicle trajectory time-space alignment device according to an embodiment of this application.

[0023] Figure 6 The diagram shown is a schematic block diagram of a vehicle according to an embodiment of this application.

[0024] Figure 7 The diagram shown is a schematic block diagram of a computer device according to an embodiment of this application. Detailed Implementation

[0025] The technical solutions in the embodiments (or "implementations") of this application will be clearly and completely described herein with reference to the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements.

[0026] If the embodiments of this application contain terms relating to directional indications or positional relationships (such as up, down, left, right, front, back, inside, outside, top, bottom, center, vertical, horizontal, longitudinal, transverse, length, width, counterclockwise, clockwise, axial, radial, circumferential, etc.), such terms are only used to explain the relative positional relationships and movement of the components in a specific posture (as shown in the attached figures); if the specific posture changes, the directional indications or positional relationships will also change accordingly. Furthermore, the terms "first" and "second" used in the embodiments of this application are only for descriptive convenience and should not be construed as indicating or implying relative importance.

[0027] The vehicle trajectory time-space alignment method, apparatus, computer equipment, and vehicle of this application will be described in detail below with reference to the accompanying drawings. Unless otherwise specified, the features of the following embodiments and implementations can be combined with each other.

[0028] Figure 1 A flowchart illustrating a vehicle trajectory temporal-spatial alignment method according to an embodiment of this application is provided. See also... Figure 1 As shown, a vehicle trajectory time-space alignment method according to an embodiment of this application may include steps S1 to S5.

[0029] In step S1, sparse first trajectory reference points output by the planning module are obtained. The time interval between two adjacent first trajectory reference points is the planning period of the planning module. In this embodiment, the planning period can be, for example, 100ms (milliseconds). The information of the first trajectory reference points may include the vehicle's first reference lateral position, first reference heading angle, and first reference longitudinal velocity.

[0030] In step S2, time interpolation is performed between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points. The time interval between two adjacent second trajectory reference points is the control cycle of the chassis control module, which is shorter than the planning cycle. In this embodiment, the control cycle can be, for example, 10ms. The information of the second trajectory reference points may include the vehicle's second reference lateral position, second reference heading angle, and second reference longitudinal velocity.

[0031] In step S3, during the time interval when the planning cycle and the control cycle run asynchronously, the current pose information of the vehicle in the global coordinate system is deduced based on the vehicle planar motion model.

[0032] In step S4, based on the current pose information of the vehicle obtained from the deduction, the coordinates of the second trajectory reference point are transformed so that the second trajectory reference point is projected from the global coordinate system to the current vehicle body coordinate system.

[0033] In step S5, a reference trajectory sequence aligned with the control cycle is output for the chassis control module to perform trajectory tracking control.

[0034] Using the above method, this application can receive sparse first trajectory reference points output by the planning module. Since the planning cycle of the planning module is longer than the control cycle of the chassis control module, the amount of trajectory data transmitted from the planning module to the chassis control module can be reduced, thus reducing the communication burden between the two. Furthermore, when the planning cycle and control cycle are inconsistent, a denser set of second trajectory reference points corresponding to the control cycle is generated by time interpolation between adjacent first trajectory reference points, enabling continuous and high-resolution reconstruction of the reference trajectory in the time dimension. Simultaneously, coordinate transformation is performed on the reference trajectory based on the vehicle's current pose information, achieving spatial alignment of the reference trajectory.

[0035] Therefore, the chassis control module can obtain a continuous, smooth, and executable reference trajectory that matches the current control cycle under highly dynamic operating conditions, thereby improving the stability and accuracy of trajectory tracking control. Thus, the vehicle trajectory time-space alignment method of this application is applicable to active safety scenarios such as high-speed obstacle avoidance and emergency lane changes.

[0036] In an optional embodiment, see Figure 2 As shown, step S2, which involves time interpolation between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points, may include step S21.

[0037] In step S21, based on the time information of two adjacent first trajectory reference points, time interpolation is performed on the first reference lateral position, first reference heading angle and first reference longitudinal velocity of the two adjacent first trajectory reference points to obtain the second reference lateral position, second reference heading angle and second reference longitudinal velocity of multiple second trajectory reference points corresponding to the control cycle.

[0038] Specifically, the first trajectory reference point can be represented as:

[0039] in, This is the vehicle's first reference lateral position. This is the vehicle's first reference heading angle. The first reference longitudinal velocity of the vehicle, The planning period is N, and the number of reference points for the first trajectory is N.

[0040] For any control moment When it is located at two adjacent planning time nodes and In between, the reference trajectory can be reconstructed using the following interpolation relationship to obtain multiple denser second trajectory reference points. The following interpolation relationship is illustrated using time interpolation of the first reference lateral position of the vehicle between two adjacent first trajectory reference points as an example:

[0041] in:

[0042] Therefore, according to the corresponding control time The first reference lateral position of the vehicle for two adjacent first trajectory reference points. By performing time interpolation, multiple second reference lateral positions corresponding to the control cycle can be obtained.

[0043] A similar approach can be used to determine the first reference heading angle for two adjacent first trajectory reference points. and the first reference longitudinal velocity By performing time interpolation, multiple second reference heading angles and second reference longitudinal velocities corresponding to the control cycle can be obtained, thereby generating information on multiple second trajectory reference points corresponding to the control cycle.

[0044] Using the above method, multiple denser second trajectory reference points are generated between two adjacent first trajectory reference points through time interpolation, so that the time interval between two adjacent second trajectory reference points is consistent with the control cycle of the chassis control module, thereby ensuring the continuity of the reference trajectory in the time dimension and maintaining smooth changes in the spatial dimension.

[0045] In an optional embodiment, based on the time information of two adjacent first trajectory reference points, the Piecewise Cubic Hermite Interpolating Polynomial (PCHIP) method can be used to perform time interpolation calculations on the first reference lateral position, first reference heading angle, and first reference longitudinal velocity of the two adjacent first trajectory reference points, thereby obtaining information on multiple second trajectory reference points.

[0046] By employing the above methods, the second trajectory reference point can be made to have continuity in the time dimension and smoothness in the spatial dimension, and the overshoot caused by traditional spline interpolation in high curvature scenarios can be avoided, thereby improving the stability and executability of the reference trajectory in high dynamic conditions such as emergency obstacle avoidance.

[0047] In an optional embodiment, see Figure 3 As shown, step S3, which involves deriving the vehicle's current pose information in the global coordinate system based on the vehicle's planar motion model, may include steps S31 to S34.

[0048] In step S31, a planar motion model of the vehicle is established.

[0049] The vehicle's planar motion model can be represented as:

[0050] in, The longitudinal speed of the vehicle. The lateral speed of the vehicle. Let yaw rate be the vehicle's angular velocity. The rate of change of the vehicle's heading angle, This represents the rate of change of the vehicle's position in the global coordinate system.

[0051] In step S32, the actual lateral speed, actual longitudinal speed, and actual yaw rate of the vehicle are obtained.

[0052] In step S33, based on the actual lateral speed, actual longitudinal speed and actual yaw rate of the vehicle obtained in step S32, the vehicle's position change rate and heading angle change rate in the global coordinate system can be calculated using the vehicle planar motion model established in step S31.

[0053] In step S34, the position change rate and heading angle change rate calculated in step S33 are integrated over time to obtain the relative pose estimate of the vehicle in the global coordinate system relative to the most recent synchronization time:

[0054] The relative pose estimate includes the vehicle's current position and current heading angle. This relative pose estimate serves as the derived current pose information of the vehicle in the global coordinate system.

[0055] Within the time interval between two adjacent first trajectory reference points, when the planning cycle and control cycle run asynchronously, for example, for a planning cycle of 100ms and a control cycle of 10ms, during the time interval between the 100ms and 200ms planning cycle, specifically at the times corresponding to the 110ms, 120ms, ... up to the 190ms, since the real-time pose information of the vehicle cannot be obtained, the above pose deduction method can be used to estimate the current pose of the vehicle at the corresponding time, thereby providing a state basis for the spatial alignment of subsequent trajectories and reducing the dependence on strict clock synchronization and high-frequency perception updates.

[0056] In an optional embodiment, after the current pose information of the vehicle in the global coordinate system is obtained by deduction, step S3 may further include step S35.

[0057] In step S35, during the pose estimation process, when the control cycle and the planning cycle are realigned, the relative pose estimate of the vehicle relative to the most recent synchronization time is reset to zero.

[0058] When the vehicle reaches the next planned time node, the control cycle and planning cycle are resynchronized. At this time, the vehicle can acquire the actual pose information, namely the corresponding first reference lateral position, first reference heading angle, and first reference longitudinal velocity. By resetting this relative pose estimate to zero, the cumulative error introduced by the integral operation during pose estimation can be effectively suppressed, thereby improving the accuracy of pose estimation under the condition of different planning and control cycles.

[0059] In an optional embodiment, see Figure 4 As shown, step S4, which involves performing coordinate transformation on the second trajectory reference point based on the vehicle's current pose information so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system, may include step S41.

[0060] The coordinate transformation includes a rotation transformation based on the vehicle's current heading angle and a translation transformation based on the vehicle's current position. Specifically, in step S41, based on the vehicle's current pose information, the second trajectory reference point undergoes a rotation transformation based on the current heading angle and a translation transformation based on the vehicle's current position, thereby projecting the second trajectory reference point from the global coordinate system to the vehicle's current body coordinate system. The coordinate projection relationship can be expressed as:

[0061] in, This represents the position of the second trajectory point projected onto the vehicle body coordinate system. Let this be the position of the second trajectory point in the global coordinate system. This refers to the vehicle's current pose information in the global coordinate system.

[0062] The heading angle projected onto the vehicle coordinate system from the second trajectory point can be expressed as:

[0063] Through the above coordinate projection process, the chassis control module can obtain a reference trajectory sequence that is consistent in time and space in the current vehicle body coordinate system in each control cycle. This allows the controller to directly calculate the position error and heading angle error relative to the current reference trajectory point, thereby providing a stable, continuous, and physically meaningful input for subsequent trajectory tracking control and multi-actuator coordinated control.

[0064] In this application, the planning period of the first trajectory reference point output by the planning module is different from the control period of the control commands output by the chassis control module. Based on this, the control period is divided into synchronous period and asynchronous period: when the planning period and the control period are aligned, the control period is synchronous; when the planning period and the control period are not aligned, the control period is asynchronous.

[0065] To address the issue that planned trajectories cannot be directly used for control within asynchronous cycles, this application generates a second trajectory reference point between two adjacent first trajectory reference points, thereby achieving dynamic reconstruction of the reference trajectory. This solves the problems of trajectory lag, lack of control reference, or erroneous reference under different cycle conditions, and provides a stable reference input basis for highly dynamic active safety control.

[0066] Thanks to the above design, the planning module only needs to periodically send a small number of sparse first trajectory reference points. Based on the time information of the first trajectory reference points, the chassis control module reconstructs a high-frequency reference trajectory sequence that is strictly aligned with the control cycle using time interpolation. Without increasing the burden on CAN (Controller Area Network) communication, continuous and high-resolution reconstruction of the trajectory in the time dimension is achieved, enabling the chassis control module to obtain a smooth, continuous, and predictable reference trajectory under highly dynamic operating conditions.

[0067] During the asynchronous cycle, the chassis control module can extrapolate and estimate the vehicle's pose at various moments within the asynchronous cycle based on the vehicle's current pose information, control input, and vehicle planar motion model at the most recent synchronization moment. This allows the vehicle to obtain pose information consistent with the current control cycle without relying on additional sensors or planning updates, providing the necessary state basis for trajectory space alignment and reducing the system's dependence on strict clock synchronization and high-frequency perception feedback.

[0068] In the asynchronous cycle, after obtaining the vehicle's current pose information, this application further proposes a trajectory spatial projection method based on real-time vehicle pose. This method dynamically maps the reference trajectory defined in the global coordinate system on the planning side to the current vehicle body coordinate system, achieving consistent alignment of the trajectory in spatial dimensions. This spatial alignment mechanism ensures that the spatial definition of the reference trajectory remains consistent with the controller's internal state calculations, effectively avoiding distortions in lateral and heading error calculations caused by coordinate system mismatch. This improves the stability and consistency of trajectory tracking control under high-dynamic conditions.

[0069] This application also provides a vehicle trajectory time-space alignment device 500. Figure 5 A schematic block diagram of a vehicle trajectory temporal-spatial alignment device 500 according to one embodiment of this application is shown. Figure 5 As shown, a vehicle trajectory time-space alignment device 500 according to one embodiment of this application may include a trajectory data receiving module 501, a trajectory reconstruction module 502, a pose inference module 503, a coordinate transformation module 504, and an output module 505.

[0070] The trajectory data receiving module 501 can be used to obtain sparse first trajectory reference points output by the planning module, and the time interval between two adjacent first trajectory reference points is the planning period of the planning module.

[0071] The trajectory reconstruction module 502 can perform time interpolation between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points. The time interval between two adjacent second trajectory reference points is the control cycle of the chassis control module, and the control cycle is less than the planning cycle.

[0072] The pose inference module 503 can infer the current pose information of the vehicle in the global coordinate system based on the vehicle planar motion model within the time interval during which the planning cycle and control cycle run asynchronously.

[0073] The coordinate transformation module 504 can perform coordinate transformation on the second trajectory reference point according to the current pose information of the vehicle, so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system.

[0074] The output module 505 can be used to output a reference trajectory sequence aligned with the control cycle for the chassis control module to perform trajectory tracking control.

[0075] This application also provides a vehicle. Figure 6 A schematic block diagram of a vehicle 600 according to one embodiment of this application is shown. Figure 6 As shown, a vehicle 600 according to one embodiment of this application includes a vehicle trajectory time-space alignment device 500 as described above.

[0076] In some embodiments, the vehicle 600 of this application may further include a planning module 601 and a chassis control module 602. The planning module 601 is connected to the chassis control module 602 via a vehicle trajectory time-space alignment device 500. The planning module 601 can be used to generate sparse first trajectory reference points and send them to the vehicle trajectory time-space alignment device 500. The chassis control module 602 can perform trajectory tracking control based on the reference trajectory sequence output by the vehicle trajectory time-space alignment device 500.

[0077] This application also provides a computer device 700. Figure 7 A schematic block diagram of a computer device 700 according to one embodiment of this application is shown. Figure 7As shown, a computer device 700 according to one embodiment of this application includes a processor 701, an internal bus 702, a network interface 703, a memory 704, and a non-volatile memory 705. It may also include other hardware required for various services. The processor 701 can read the corresponding computer program from the non-volatile memory 705 into the memory 704 and then run it to implement the steps of the vehicle trajectory time-space alignment method described above. Of course, besides software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution entity of the following processing flow is not limited to individual logic units, but can also be hardware or logic components.

[0078] The vehicle trajectory time-space alignment device 500, vehicle 600 and computer equipment 700 of this application can have similar beneficial technical effects as the vehicle trajectory time-space alignment method described above, so they will not be described in detail here.

[0079] It should be noted that the technical solutions or features described in the above embodiments can be combined or complemented by each other without conflict. The scope of protection of this application is not limited to the specific structures shown in the above embodiments and drawings; all modifications, equivalent substitutions or improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for time-space alignment of vehicle trajectories, characterized in that: include: Obtain the sparse first trajectory reference points output by the planning module, and the time interval between two adjacent first trajectory reference points is the planning period of the planning module; Time interpolation is performed between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points, wherein the time interval between two adjacent second trajectory reference points is the control cycle of the chassis control module, and the control cycle is less than the planning cycle. During the time interval in which the planning cycle and the control cycle run asynchronously, the current pose information of the vehicle in the global coordinate system is deduced based on the vehicle planar motion model. Based on the vehicle's current pose information, the coordinates of the second trajectory reference point are transformed so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system. Output a reference trajectory sequence aligned with the control cycle for the chassis control module to perform trajectory tracking control.

2. The vehicle trajectory time-space alignment method according to claim 1, characterized in that, The information for each first trajectory reference point includes the vehicle's first reference lateral position, first reference heading angle, and first reference longitudinal velocity; the information for each second trajectory reference point includes the vehicle's second reference lateral position, second reference heading angle, and second reference longitudinal velocity. The step of performing time interpolation between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points includes: Based on the time information of two adjacent first trajectory reference points, time interpolation is performed on the first reference lateral position, the first reference heading angle and the first reference longitudinal velocity of the two adjacent first trajectory reference points to obtain multiple second reference lateral positions, second reference heading angles and second reference longitudinal velocities corresponding to the control cycle.

3. The vehicle trajectory time-space alignment method according to claim 2, characterized in that, Based on the time information of two adjacent first trajectory reference points, the piecewise cubic Hermite interpolation method is used to interpolate the time of the first reference lateral position, the first reference heading angle and the first reference longitudinal velocity of the two adjacent first trajectory reference points.

4. The vehicle trajectory time-space alignment method according to claim 1, characterized in that, The deduction of the vehicle's current pose information in the global coordinate system based on the vehicle's planar motion model includes: Establish a planar motion model of the vehicle; Obtain the vehicle's actual lateral speed, actual longitudinal speed, and actual yaw rate; Based on the actual lateral travel speed, the actual longitudinal travel speed, and the actual yaw rate, the vehicle's position change rate and heading angle change rate in the global coordinate system are calculated using the vehicle planar motion model. The rate of change of position and the rate of change of heading angle are integrated over time to obtain the relative pose estimate of the vehicle in the global coordinate system relative to the most recent synchronization time. The relative pose estimate includes the current position and current heading angle of the vehicle, and the relative pose estimate serves as the derived current pose information of the vehicle in the global coordinate system.

5. The vehicle trajectory time-space alignment method according to claim 4, characterized in that, Also includes: During pose estimation, when the control cycle is realigned with the planning cycle, the relative pose estimate of the vehicle relative to the most recent synchronization time is reset to zero.

6. The vehicle trajectory time-space alignment method according to claim 4, characterized in that, The step of performing coordinate transformation on the second trajectory reference point based on the vehicle's current pose information, so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system, includes: Based on the vehicle's current pose information, the second trajectory reference point is subjected to a rotation transformation based on the current heading angle and a translation transformation based on the vehicle's current position, so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the vehicle trajectory time-space alignment method as described in any one of claims 1 to 6.

8. A vehicle trajectory time-space alignment device, characterized in that, include: The trajectory data receiving module is used to obtain sparse first trajectory reference points output by the planning module, and the time interval between two adjacent first trajectory reference points is the planning period of the planning module. The trajectory reconstruction module is used to perform time interpolation between two adjacent first trajectory reference points to generate multiple dense second trajectory reference points, wherein the time interval between two adjacent second trajectory reference points is the control cycle of the chassis control module, and the control cycle is less than the planning cycle. The pose estimation module is used to estimate the current pose information of the vehicle in the global coordinate system based on the vehicle planar motion model during the time interval between the asynchronous operation of the planning cycle and the control cycle. The coordinate transformation module is used to transform the coordinates of the second trajectory reference point according to the current pose information of the vehicle, so that the second trajectory reference point is uniformly projected onto the current vehicle body coordinate system. The output module is used to output a reference trajectory sequence aligned with the control cycle for the chassis control module to perform trajectory tracking control.

9. A vehicle, characterized in that, The vehicle includes the vehicle trajectory time-space alignment device as described in claim 8.

10. The vehicle according to claim 9, characterized in that, It also includes a planning module and a chassis control module. The planning module is connected to the chassis control module through the vehicle trajectory time-space alignment device. The planning module is used to generate sparse first trajectory reference points and send them to the vehicle trajectory time-space alignment device. The chassis control module is used to perform trajectory tracking control based on the reference trajectory sequence output by the vehicle trajectory time-space alignment device.

Images